CAMEL: A Weakly Supervised Learning Framework for Histopathology Image Segmentation

Gang Xu, Zhigang Song, Zhuo Sun, Calvin Ku, Zhe Yang, Cancheng Liu, Shuhao Wang, Jianpeng Ma, Wei Xu; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 10682-10691


Histopathology image analysis plays a critical role in cancer diagnosis and treatment. To automatically segment the cancerous regions, fully supervised segmentation algorithms require labor-intensive and time-consuming labeling at the pixel level. In this research, we propose CAMEL, a weakly supervised learning framework for histopathology image segmentation using only image-level labels. Using multiple instance learning (MIL)-based label enrichment, CAMEL splits the image into latticed instances and automatically generates instance-level labels. After label enrichment, the instance-level labels are further assigned to the corresponding pixels, producing the approximate pixel-level labels and making fully supervised training of segmentation models possible. CAMEL achieves comparable performance with the fully supervised approaches in both instance-level classification and pixel-level segmentation on CAMELYON16 and a colorectal adenoma dataset. Moreover, the generality of the automatic labeling methodology may benefit future weakly supervised learning studies for histopathology image analysis.

Related Material

author = {Xu, Gang and Song, Zhigang and Sun, Zhuo and Ku, Calvin and Yang, Zhe and Liu, Cancheng and Wang, Shuhao and Ma, Jianpeng and Xu, Wei},
title = {CAMEL: A Weakly Supervised Learning Framework for Histopathology Image Segmentation},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}